© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137180
    Prev
    Next
    INDEX
    Explanations

    principles and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite

    principles preventing harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    च
    1.05
     zacz
    0.86
     đội
    0.80
     позволи
    0.77
     puesta
    0.76
     poursuivre
    0.76
     πάντα
    0.76
     bảy
    0.75
     pleinement
    0.75
     ያለ
    0.74
    POSITIVE LOGITS
    us
    1.01
    st
    0.92
    of
    0.92
    ‌است
    0.91
    </b>
    0.87
    ۵
    0.84
    </td>
    0.84
    ische
    0.82
    esi
    0.76
    ۰
    0.76
    Activations Density 0.030%

    No Known Activations